Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the async job_id pattern, cost implications (balance deduction based on duration), and diarize behavior. This is substantial transparency, though it omits failure modes and authentication requirements, which would elevate to 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three focused sentences cover purpose, key option, and behavioral notes. Front-loaded with the main action and outcome. No wasted words, though slightly dense in the third sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with async result retrieval and billing side-effects, the description covers the critical flow: submit URL, optionally diarize, get job_id, fetch via get_transcript, and note cost. Missing details like error handling and output format are minor given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all 3 parameters at 100% with decent descriptions. The description adds clarity on diarize (speaker separation) but adds nothing about language or url beyond schema. Meets baseline without significant added value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb (transcribe) and resource (audio/video via URL) with output (text with timestamps). It distinguishes from siblings by naming get_transcript as the retrieval step and implicitly contrasting with file-based transcription (transcribe_file). Purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Specifies supported platforms (YouTube, VK Video, Rutube, etc.) and directs agents to use get_transcript to fetch results. However, it does not explicitly exclude alternatives like transcribe_file for local files or create_upload for uploads, leaving some ambiguity for edge cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.